{"total":367,"rows":[{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152,"area":null},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991,"area":null},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"area":null},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710,"area":null},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2211.13445","title":"Delving into Out-of-Distribution Detection with Vision-Language Representations","created":"2022-11-24","cited_by_count":216,"area":null},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"area":null},{"id":"2310.06816","title":"Text Embeddings Reveal (Almost) As Much As Text","created":"2023-10-10","cited_by_count":192,"area":null},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187,"area":null},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184,"area":null},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177,"area":null},{"id":"2302.03084","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","created":"2023-02-06","cited_by_count":156,"area":null},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"area":null},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142,"area":null},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137,"area":null},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2212.10846","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","created":"2022-12-21","cited_by_count":115,"area":null},{"id":"2408.09647","title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection","created":"2024-08-19","cited_by_count":113,"area":null},{"id":"2305.15023","title":"Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":101,"area":null},{"id":"2208.05516","title":"Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP","created":"2022-08-10","cited_by_count":97,"area":null},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95,"area":null},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91,"area":null},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90,"area":null},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82,"area":null},{"id":"2505.05071","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","created":"2025-05-08","cited_by_count":81,"area":null},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74,"area":null},{"id":"2503.06661","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP","created":"2025-03-09","cited_by_count":73,"area":null},{"id":"2212.00836","title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","created":"2022-12-01","cited_by_count":69,"area":null},{"id":"2302.04156","title":"Prompting for Multimodal Hateful Meme Classification","created":"2023-02-08","cited_by_count":69,"area":null},{"id":"2208.02131","title":"Masked Vision and Language Modeling for Multi-modal Representation Learning","created":"2022-08-03","cited_by_count":67,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","cited_by_count":64,"area":null},{"id":"2303.17811","title":"Zero-shot Referring Image Segmentation with Global-Local Context Features","created":"2023-03-31","cited_by_count":61,"area":null},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59,"area":null},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2302.04269","title":"Diagnosing and Rectifying Vision Models using Language","created":"2023-02-08","cited_by_count":58,"area":null},{"id":"2303.05977","title":"Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models","created":"2023-03-10","cited_by_count":58,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2404.15736","title":"What Makes Multimodal In-Context Learning Work?","created":"2024-04-24","cited_by_count":56,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2212.02291","title":"I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification","created":"2022-12-05","cited_by_count":54,"area":null},{"id":"2303.05952","title":"Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning","created":"2023-03-10","cited_by_count":53,"area":null},{"id":"2304.02828","title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias","created":"2023-04-06","cited_by_count":52,"area":null},{"id":"2309.16137","title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval","created":"2023-09-28","cited_by_count":52,"area":null},{"id":"2302.09923","title":"Prompt Stealing Attacks Against Text-to-Image Generation Models","created":"2023-02-20","cited_by_count":51,"area":null},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"area":null},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49,"area":null},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49,"area":null},{"id":"2308.14430","title":"TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models","created":"2023-08-28","cited_by_count":48,"area":null},{"id":"2310.02227","title":"SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training","created":"2023-10-03","cited_by_count":47,"area":null},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46,"area":null},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46,"area":null},{"id":"2212.11261","title":"Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias","created":"2022-12-21","cited_by_count":43,"area":null},{"id":"2411.14517","title":"The Double-Ellipsoid Geometry of CLIP","created":"2024-11-21","cited_by_count":42,"area":null},{"id":"2210.07179","title":"MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2210.11603","title":"3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows","created":"2022-10-20","cited_by_count":41,"area":null},{"id":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41,"area":null},{"id":"2402.12959","title":"Prompt Stealing Attacks Against Large Language Models","created":"2024-02-20","cited_by_count":40,"area":null},{"id":"2305.17678","title":"Decoding the Underlying Meaning of Multimodal Hateful Memes","created":"2023-05-28","cited_by_count":39,"area":null},{"id":"2309.02999","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","created":"2023-09-06","cited_by_count":39,"area":null},{"id":"2411.09219","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","created":"2024-11-14","cited_by_count":39,"area":null},{"id":"2308.00353","title":"Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding","created":"2023-08-01","cited_by_count":38,"area":null},{"id":"2203.05796","title":"Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision","created":"2022-03-11","cited_by_count":36,"area":null},{"id":"2302.12971","title":"BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding","created":"2023-02-25","cited_by_count":36,"area":null},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2304.08386","title":"Progressive Visual Prompt Learning with Contrastive Feature Re-formation","created":"2023-04-17","cited_by_count":36,"area":null},{"id":"2305.08685","title":"CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding","created":"2023-05-15","cited_by_count":35,"area":null},{"id":"2403.03715","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","created":"2024-03-06","cited_by_count":35,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2307.16525","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","created":"2023-07-31","cited_by_count":34,"area":null},{"id":"2212.06858","title":"LidarCLIP or: How I Learned to Talk to Point Clouds","created":"2022-12-13","cited_by_count":33,"area":null},{"id":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33,"area":null},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33,"area":null},{"id":"2309.15564","title":"Jointly Training Large Autoregressive Multimodal Models","created":"2023-09-27","cited_by_count":32,"area":null},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30,"area":null},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"area":null},{"id":"2210.03765","title":"Visualize Before You Write: Imagination-Guided Open-Ended Text Generation","created":"2022-10-07","cited_by_count":30,"area":null},{"id":"2211.08887","title":"Stare at What You See: Masked Image Modeling without Reconstruction","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2210.11522","title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","created":"2022-10-20","cited_by_count":28,"area":null},{"id":"2304.09179","title":"Pretrained Language Models as Visual Planners for Human Assistance","created":"2023-04-17","cited_by_count":28,"area":null},{"id":"2404.19752","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","created":"2024-04-30","cited_by_count":28,"area":null},{"id":"2210.03501","title":"Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement","created":"2022-10-07","cited_by_count":27,"area":null},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2307.14331","title":"Visual Instruction Inversion: Image Editing via Visual Prompting","created":"2023-07-26","cited_by_count":26,"area":null},{"id":"2309.17430","title":"FACTS: First Amplify Correlations and Then Slice to Discover Bias","created":"2023-09-29","cited_by_count":26,"area":null},{"id":"2310.18297","title":"Image Clustering Conditioned on Text Criteria","created":"2023-10-27","cited_by_count":26,"area":null},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25,"area":null},{"id":"2305.07558","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","created":"2023-05-12","cited_by_count":25,"area":null},{"id":"2404.03242","title":"Would Deep Generative Models Amplify Bias in Future Models?","created":"2024-04-04","cited_by_count":24,"area":null},{"id":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2211.11153","title":"Unifying Vision-Language Representation Space with Single-tower Transformer","created":"2022-11-21","cited_by_count":22,"area":null},{"id":"2310.18049","title":"Text Augmented Spatial-aware Zero-shot Referring Image Segmentation","created":"2023-10-27","cited_by_count":21,"area":null},{"id":"2210.14562","title":"FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization","created":"2022-10-26","cited_by_count":20,"area":null},{"id":"2302.01328","title":"IC3: Image Captioning by Committee Consensus","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2302.14794","title":"Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning","created":"2023-02-28","cited_by_count":20,"area":null},{"id":"2307.06526","title":"AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion","created":"2023-07-13","cited_by_count":20,"area":null}],"next_cursor":"100"}